On-line ammonia nitrogen measurement using generalized additive model and stochastic configuration networks

On-line measuring of ammonia nitrogen in seawater is essential to the intensive aquaculture process. Its concentration has an important effect on the growth and development of the breeding organisms. The popular Nessler's reagent method suffers from large time delays. It can only be applied off-line. To realize on-line measurement, we propose a hybrid soft measurement model for ammonia nitrogen. This new model combines mechanism analysis and data driven methods, the generalized additive model and stochastic configuration networks are used respectively. To demonstrate the effectiveness of the proposed modelling techniques, an intensive aquaculture system is designed in laboratory to realize this soft measurement method. The accuracy of the test data performed in generalized additive model is 0.073, the accuracy after error compensation is 0.064. Compared with other methods, the stochastic configuration networks compensation model has the shortest running time which is 0.5 s. These experimental results show that the proposed hybrid method performs better than other existing data driven modeling methods, and this work will be the foundation for the practical application.